The ongoing effort to create methods for detecting and quantifying fatigue damage is motivated by the high levels of uncertainty in present fatigue-life prediction approaches and the frequently catastrophic nature of fatigue failure. The fatigue life of high strength aluminum alloy 2090-T83 is predicted in this study using a variety of artificial intelligence and machine learning techniques for constant amplitude and negative stress ratios (R ¼ À1). Artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), support-vector machines (SVM), a random forest model (RF), and an extreme-gradient tree-boosting model (XGB) are trained using numerical and experimental input data obtained from fatigue tests based on a relatively low number of stress measurements. In particular, the coefficients of the traditional force law formula are found using relevant numerical methods. It is shown that, in comparison to traditional approaches, the neural network and neuro-fuzzy models produce better results, with the neural network models trained using the boosting iterations technique providing the best performances. Building strong models from weak models, XGB helps to predict fatigue life by reducing model partiality and variation in supervised learning. Fuzzy neural models can be used to predict the fatigue life of alloys more accurately than neural networks and traditional methods.

The behavior of microstructural short fatigue cracks (20-100 µm in length on the same scale as the grain size) in the cast aluminum alloy A07710-T6 was investigated. Two heat treatment conditions have been used, an underaged and an overaged microstructure, chosen to have very similar tensile properties, so that the effects of precipitation and hence slip distribution on fatigue behavior could be studied at the same strength level. The results of short crack propagation tests performed on smooth specimens at 25℃ and R=0.1 are compared to conventional (long) fatigue crack propagation and threshold results under the same conditions. The short crack data is also compared to long crack tests conducted at constant maximum applied load (so that the R-ratio increases to a value above 0.8 as the threshold is approached). In conventional long crack tests, better low and high threshold crack propagation resistance is associated with the underaged microstructure. This behavior is also reflected in the thresholds obtained at high R.